Memorymaster — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "memorymaster",
"source": {
"kind": "package",
"origin": "memorymaster"
},
"server": {
"name": "memorymaster"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "verification-discount",
"level": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.9"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (36 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/bridges/local_search/everything.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/bridges/local_search/everything.py:142`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/bridges/local_search/everything.py"
},
"evidence": "y: result = subprocess.run( args, capture_output=True, text=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/bridges/local_search/everything.py",
"line": 142,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/bridges/local_search/provider.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/bridges/local_search/provider.py:79`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/bridges/local_search/provider.py"
},
"evidence": "rror. - Never use ``shell=True`` in subprocess calls. - Respect ``limit`` and ``kind`` filters on a best-effort",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/bridges/local_search/provider.py",
"line": 79,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/core/llm_provider.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/core/llm_provider.py:322`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/core/llm_provider.py"
},
"evidence": "try: result = subprocess.run( [bin_path, \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/core/llm_provider.py",
"line": 322,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/govern/claim_verifier.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/govern/claim_verifier.py:60`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/govern/claim_verifier.py"
},
"evidence": "try: result = subprocess.run( [\"rg\", \"-l\", \"--type-add\", \"code:*.{ts,js,py,tsx,jsx,go,rs}\", \"-t\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/govern/claim_verifier.py",
"line": 60,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/govern/jobs/staleness.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/govern/jobs/staleness.py:61`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/govern/jobs/staleness.py"
},
"evidence": "try: result = subprocess.run( [ \"git\", \"log\", \"--oneline\", \"--since\", since_iso,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/govern/jobs/staleness.py",
"line": 61,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/govern/scheduler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/govern/scheduler.py:19`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/govern/scheduler.py"
},
"evidence": "ry: root_proc = subprocess.run( [\"git\", \"-C\", str(resolved), \"rev-parse\", \"--show-toplevel\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/govern/scheduler.py",
"line": 19,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/govern/steward.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/govern/steward.py:1439`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/govern/steward.py"
},
"evidence": "try: proc = subprocess.run( [\"git\", \"-C\", str(resolved), \"rev-parse\", \"HEAD\"], captu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/govern/steward.py",
"line": 1439,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/stores/snapshot.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/stores/snapshot.py:33`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/stores/snapshot.py"
},
"evidence": "try: proc = subprocess.run( [\"git\", \"-C\", str(resolved), \"rev-parse\", \"HEAD\"], captu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/stores/snapshot.py",
"line": 33,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/surfaces/dashboard.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/surfaces/dashboard.py:746`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/surfaces/dashboard.py"
},
"evidence": "self._operator_proc = subprocess.Popen( # noqa: S603 cmd, stdout=subprocess.DEVNULL,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/surfaces/dashboard.py",
"line": 746,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (memorymaster/surfaces/setup_detect.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`memorymaster/surfaces/setup_detect.py:68`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "memorymaster/surfaces/setup_detect.py"
},
"evidence": "try: result = subprocess.run( args, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "memorymaster/surfaces/setup_detect.py",
"line": 68,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"memorymaster\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "memorymaster"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "init_db",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_claim",
"tags": [],
"reasons": {}
},
{
"tool": "checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "archive_by_source",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_project",
"tags": [],
"reasons": {}
},
{
"tool": "local_search",
"tags": [],
"reasons": {}
},
{
"tool": "run_cycle",
"tags": [],
"reasons": {}
},
{
"tool": "run_steward",
"tags": [],
"reasons": {}
},
{
"tool": "classify_query",
"tags": [],
"reasons": {}
},
{
"tool": "query_memory",
"tags": [],
"reasons": {}
},
{
"tool": "query_claim_paths",
"tags": [],
"reasons": {}
},
{
"tool": "recall_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "query_for_context",
"tags": [],
"reasons": {}
},
{
"tool": "volunteer_context",
"tags": [],
"reasons": {}
},
{
"tool": "query_for_task",
"tags": [],
"reasons": {}
},
{
"tool": "read_active_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "list_claims",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_rule",
"tags": [],
"reasons": {}
},
{
"tool": "query_rules",
"tags": [],
"reasons": {}
},
{
"tool": "rules_export",
"tags": [],
"reasons": {}
},
{
"tool": "redact_claim_payload",
"tags": [],
"reasons": {}
},
{
"tool": "pin_claim",
"tags": [],
"reasons": {}
},
{
"tool": "compact_memory",
"tags": [],
"reasons": {}
},
{
"tool": "list_events",
"tags": [],
"reasons": {}
},
{
"tool": "search_verbatim",
"tags": [],
"reasons": {}
},
{
"tool": "get_usage_rollup",
"tags": [],
"reasons": {}
},
{
"tool": "open_dashboard",
"tags": [],
"reasons": {}
},
{
"tool": "list_steward_proposals",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_steward_proposal",
"tags": [],
"reasons": {}
},
{
"tool": "extract_entities",
"tags": [],
"reasons": {}
},
{
"tool": "entity_stats",
"tags": [],
"reasons": {}
},
{
"tool": "find_related_claims",
"tags": [],
"reasons": {}
},
{
"tool": "quality_scores",
"tags": [],
"reasons": {}
},
{
"tool": "recompute_tiers",
"tags": [],
"reasons": {}
},
{
"tool": "query_meta_decisions",
"tags": [],
"reasons": {}
},
{
"tool": "federated_query",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8812ba22329a0eb42222645615265e4d649a62eb2feee9605fa1a2aee847a147",
"stats": {
"tools": 36,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 0,
"low": 0,
"info": 1
}
}
}